Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block

Pull core block/IO updates from Jens Axboe:
 "This is the main pull request for the block layer for 4.13. Not a huge
  round in terms of features, but there's a lot of churn related to some
  core cleanups.

  Note this depends on the UUID tree pull request, that Christoph
  already sent out.

  This pull request contains:

   - A series from Christoph, unifying the error/stats codes in the
     block layer. We now use blk_status_t everywhere, instead of using
     different schemes for different places.

   - Also from Christoph, some cleanups around request allocation and IO
     scheduler interactions in blk-mq.

   - And yet another series from Christoph, cleaning up how we handle
     and do bounce buffering in the block layer.

   - A blk-mq debugfs series from Bart, further improving on the support
     we have for exporting internal information to aid debugging IO
     hangs or stalls.

   - Also from Bart, a series that cleans up the request initialization
     differences across types of devices.

   - A series from Goldwyn Rodrigues, allowing the block layer to return
     failure if we will block and the user asked for non-blocking.

   - Patch from Hannes for supporting setting loop devices block size to
     that of the underlying device.

   - Two series of patches from Javier, fixing various issues with
     lightnvm, particular around pblk.

   - A series from me, adding support for write hints. This comes with
     NVMe support as well, so applications can help guide data placement
     on flash to improve performance, latencies, and write
     amplification.

   - A series from Ming, improving and hardening blk-mq support for
     stopping/starting and quiescing hardware queues.

   - Two pull requests for NVMe updates. Nothing major on the feature
     side, but lots of cleanups and bug fixes. From the usual crew.

   - A series from Neil Brown, greatly improving the bio rescue set
     support. Most notably, this kills the bio rescue work queues, if we
     don't really need them.

   - Lots of other little bug fixes that are all over the place"

* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
  lightnvm: pblk: set line bitmap check under debug
  lightnvm: pblk: verify that cache read is still valid
  lightnvm: pblk: add initialization check
  lightnvm: pblk: remove target using async. I/Os
  lightnvm: pblk: use vmalloc for GC data buffer
  lightnvm: pblk: use right metadata buffer for recovery
  lightnvm: pblk: schedule if data is not ready
  lightnvm: pblk: remove unused return variable
  lightnvm: pblk: fix double-free on pblk init
  lightnvm: pblk: fix bad le64 assignations
  nvme: Makefile: remove dead build rule
  blk-mq: map all HWQ also in hyperthreaded system
  nvmet-rdma: register ib_client to not deadlock in device removal
  nvme_fc: fix error recovery on link down.
  nvmet_fc: fix crashes on bad opcodes
  nvme_fc: Fix crash when nvme controller connection fails.
  nvme_fc: replace ioabort msleep loop with completion
  nvme_fc: fix double calls to nvme_cleanup_cmd()
  nvme-fabrics: verify that a controller returns the correct NQN
  nvme: simplify nvme_dev_attrs_are_visible
  ...

10 files changed, 231 insertions, 95 deletions

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index ff1f97006322..35f930db3c02 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -336,7 +336,7 @@ out:
 
 static void nvmet_execute_identify_nslist(struct nvmet_req *req)
 {
-	static const int buf_size = 4096;
+	static const int buf_size = NVME_IDENTIFY_DATA_SIZE;
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 	struct nvmet_ns *ns;
 	u32 min_nsid = le32_to_cpu(req->cmd->identify.nsid);
@@ -367,6 +367,64 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static u16 nvmet_copy_ns_identifier(struct nvmet_req *req, u8 type, u8 len,
+				    void *id, off_t *off)
+{
+	struct nvme_ns_id_desc desc = {
+		.nidt = type,
+		.nidl = len,
+	};
+	u16 status;
+
+	status = nvmet_copy_to_sgl(req, *off, &desc, sizeof(desc));
+	if (status)
+		return status;
+	*off += sizeof(desc);
+
+	status = nvmet_copy_to_sgl(req, *off, id, len);
+	if (status)
+		return status;
+	*off += len;
+
+	return 0;
+}
+
+static void nvmet_execute_identify_desclist(struct nvmet_req *req)
+{
+	struct nvmet_ns *ns;
+	u16 status = 0;
+	off_t off = 0;
+
+	ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid);
+	if (!ns) {
+		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
+		goto out;
+	}
+
+	if (memchr_inv(&ns->uuid, 0, sizeof(ns->uuid))) {
+		status = nvmet_copy_ns_identifier(req, NVME_NIDT_UUID,
+						  NVME_NIDT_UUID_LEN,
+						  &ns->uuid, &off);
+		if (status)
+			goto out_put_ns;
+	}
+	if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) {
+		status = nvmet_copy_ns_identifier(req, NVME_NIDT_NGUID,
+						  NVME_NIDT_NGUID_LEN,
+						  &ns->nguid, &off);
+		if (status)
+			goto out_put_ns;
+	}
+
+	if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off,
+			off) != NVME_IDENTIFY_DATA_SIZE - off)
+		status = NVME_SC_INTERNAL | NVME_SC_DNR;
+out_put_ns:
+	nvmet_put_namespace(ns);
+out:
+	nvmet_req_complete(req, status);
+}
+
 /*
  * A "mimimum viable" abort implementation: the command is mandatory in the
  * spec, but we are not required to do any useful work.  We couldn't really
@@ -504,7 +562,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		}
 		break;
 	case nvme_admin_identify:
-		req->data_len = 4096;
+		req->data_len = NVME_IDENTIFY_DATA_SIZE;
 		switch (cmd->identify.cns) {
 		case NVME_ID_CNS_NS:
 			req->execute = nvmet_execute_identify_ns;
@@ -515,6 +573,9 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		case NVME_ID_CNS_NS_ACTIVE_LIST:
 			req->execute = nvmet_execute_identify_nslist;
 			return 0;
+		case NVME_ID_CNS_NS_DESC_LIST:
+			req->execute = nvmet_execute_identify_desclist;
+			return 0;
 		}
 		break;
 	case nvme_admin_abort_cmd:
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index be8c800078e2..a358ecd93e11 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -305,11 +305,41 @@ out_unlock:
 
 CONFIGFS_ATTR(nvmet_ns_, device_path);
 
+static ssize_t nvmet_ns_device_uuid_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%pUb\n", &to_nvmet_ns(item)->uuid);
+}
+
+static ssize_t nvmet_ns_device_uuid_store(struct config_item *item,
+					  const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	struct nvmet_subsys *subsys = ns->subsys;
+	int ret = 0;
+
+
+	mutex_lock(&subsys->lock);
+	if (ns->enabled) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+
+	if (uuid_parse(page, &ns->uuid))
+		ret = -EINVAL;
+
+out_unlock:
+	mutex_unlock(&subsys->lock);
+	return ret ? ret : count;
+}
+
 static ssize_t nvmet_ns_device_nguid_show(struct config_item *item, char *page)
 {
 	return sprintf(page, "%pUb\n", &to_nvmet_ns(item)->nguid);
 }
 
+CONFIGFS_ATTR(nvmet_ns_, device_uuid);
+
 static ssize_t nvmet_ns_device_nguid_store(struct config_item *item,
 		const char *page, size_t count)
 {
@@ -379,6 +409,7 @@ CONFIGFS_ATTR(nvmet_ns_, enable);
 static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_device_path,
 	&nvmet_ns_attr_device_nguid,
+	&nvmet_ns_attr_device_uuid,
 	&nvmet_ns_attr_enable,
 	NULL,
 };
@@ -619,8 +650,45 @@ out_unlock:
 
 CONFIGFS_ATTR(nvmet_subsys_, attr_allow_any_host);
 
+static ssize_t nvmet_subsys_version_show(struct config_item *item,
+					      char *page)
+{
+	struct nvmet_subsys *subsys = to_subsys(item);
+
+	if (NVME_TERTIARY(subsys->ver))
+		return snprintf(page, PAGE_SIZE, "%d.%d.%d\n",
+				(int)NVME_MAJOR(subsys->ver),
+				(int)NVME_MINOR(subsys->ver),
+				(int)NVME_TERTIARY(subsys->ver));
+	else
+		return snprintf(page, PAGE_SIZE, "%d.%d\n",
+				(int)NVME_MAJOR(subsys->ver),
+				(int)NVME_MINOR(subsys->ver));
+}
+
+static ssize_t nvmet_subsys_version_store(struct config_item *item,
+					       const char *page, size_t count)
+{
+	struct nvmet_subsys *subsys = to_subsys(item);
+	int major, minor, tertiary = 0;
+	int ret;
+
+
+	ret = sscanf(page, "%d.%d.%d\n", &major, &minor, &tertiary);
+	if (ret != 2 && ret != 3)
+		return -EINVAL;
+
+	down_write(&nvmet_config_sem);
+	subsys->ver = NVME_VS(major, minor, tertiary);
+	up_write(&nvmet_config_sem);
+
+	return count;
+}
+CONFIGFS_ATTR(nvmet_subsys_, version);
+
 static struct configfs_attribute *nvmet_subsys_attrs[] = {
 	&nvmet_subsys_attr_attr_allow_any_host,
+	&nvmet_subsys_attr_version,
 	NULL,
 };
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index eb9399ac97cf..b5b4ac103748 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -380,6 +380,7 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 
 	ns->nsid = nsid;
 	ns->subsys = subsys;
+	uuid_gen(&ns->uuid);
 
 	return ns;
 }
@@ -926,7 +927,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
 	if (!subsys)
 		return NULL;
 
-	subsys->ver = NVME_VS(1, 2, 1); /* NVMe 1.2.1 */
+	subsys->ver = NVME_VS(1, 3, 0); /* NVMe 1.3.0 */
 
 	switch (type) {
 	case NVME_NQN_NVME:
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 1aaf597e81fc..8f3b57b4c97b 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -53,7 +53,7 @@ static void nvmet_format_discovery_entry(struct nvmf_disc_rsp_page_hdr *hdr,
 	e->portid = port->disc_addr.portid;
 	/* we support only dynamic controllers */
 	e->cntlid = cpu_to_le16(NVME_CNTLID_DYNAMIC);
-	e->asqsz = cpu_to_le16(NVMF_AQ_DEPTH);
+	e->asqsz = cpu_to_le16(NVME_AQ_DEPTH);
 	e->subtype = type;
 	memcpy(e->trsvcid, port->disc_addr.trsvcid, NVMF_TRSVCID_SIZE);
 	memcpy(e->traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
@@ -185,7 +185,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 	case nvme_admin_identify:
-		req->data_len = 4096;
+		req->data_len = NVME_IDENTIFY_DATA_SIZE;
 		switch (cmd->identify.cns) {
 		case NVME_ID_CNS_CTRL:
 			req->execute =
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 2006fae61980..7692a96c9065 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -2096,20 +2096,22 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 	/* clear any response payload */
 	memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));
 
+	fod->data_sg = NULL;
+	fod->data_sg_cnt = 0;
+
 	ret = nvmet_req_init(&fod->req,
 				&fod->queue->nvme_cq,
 				&fod->queue->nvme_sq,
 				&nvmet_fc_tgt_fcp_ops);
-	if (!ret) {	/* bad SQE content or invalid ctrl state */
-		nvmet_fc_abort_op(tgtport, fod);
+	if (!ret) {
+		/* bad SQE content or invalid ctrl state */
+		/* nvmet layer has already called op done to send rsp. */
 		return;
 	}
 
 	/* keep a running counter of tail position */
 	atomic_inc(&fod->queue->sqtail);
 
-	fod->data_sg = NULL;
-	fod->data_sg_cnt = 0;
 	if (fod->total_length) {
 		ret = nvmet_fc_alloc_tgt_pgs(fod);
 		if (ret) {
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 294a6611fb24..1bb9d5b311b1 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -569,7 +569,6 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport,
 			struct nvmefc_tgt_fcp_req *tgt_fcpreq)
 {
 	struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
-	int active;
 
 	/*
 	 * mark aborted only in case there were 2 threads in transport
@@ -577,7 +576,6 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport,
 	 * after the abort request
 	 */
 	spin_lock(&tfcp_req->reqlock);
-	active = tfcp_req->active;
 	tfcp_req->aborted = true;
 	spin_unlock(&tfcp_req->reqlock);
 
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c
index c77940d80fc8..40128793e613 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd.c
@@ -21,7 +21,7 @@ static void nvmet_bio_done(struct bio *bio)
 	struct nvmet_req *req = bio->bi_private;
 
 	nvmet_req_complete(req,
-		bio->bi_error ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+		bio->bi_status ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
 
 	if (bio != &req->inline_bio)
 		bio_put(bio);
@@ -145,7 +145,7 @@ static void nvmet_execute_discard(struct nvmet_req *req)
 		bio->bi_private = req;
 		bio->bi_end_io = nvmet_bio_done;
 		if (status) {
-			bio->bi_error = -EIO;
+			bio->bi_status = BLK_STS_IOERR;
 			bio_endio(bio);
 		} else {
 			submit_bio(bio);
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index e503cfff0337..5f55c683b338 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -21,8 +21,6 @@
 #include "../host/nvme.h"
 #include "../host/fabrics.h"
 
-#define NVME_LOOP_AQ_DEPTH		256
-
 #define NVME_LOOP_MAX_SEGMENTS		256
 
 /*
@@ -31,7 +29,7 @@
  */
 #define NVME_LOOP_NR_AEN_COMMANDS	1
 #define NVME_LOOP_AQ_BLKMQ_DEPTH	\
-	(NVME_LOOP_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS)
+	(NVME_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS)
 
 struct nvme_loop_iod {
 	struct nvme_request	nvme_req;
@@ -45,7 +43,6 @@ struct nvme_loop_iod {
 };
 
 struct nvme_loop_ctrl {
-	spinlock_t		lock;
 	struct nvme_loop_queue	*queues;
 	u32			queue_count;
 
@@ -59,7 +56,6 @@ struct nvme_loop_ctrl {
 
 	struct nvmet_ctrl	*target_ctrl;
 	struct work_struct	delete_work;
-	struct work_struct	reset_work;
 };
 
 static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
@@ -151,7 +147,7 @@ nvme_loop_timeout(struct request *rq, bool reserved)
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(rq);
 
 	/* queue error recovery */
-	schedule_work(&iod->queue->ctrl->reset_work);
+	nvme_reset_ctrl(&iod->queue->ctrl->ctrl);
 
 	/* fail with DNR on admin cmd timeout */
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
@@ -159,17 +155,17 @@ nvme_loop_timeout(struct request *rq, bool reserved)
 	return BLK_EH_HANDLED;
 }
 
-static int nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
 	struct nvme_ns *ns = hctx->queue->queuedata;
 	struct nvme_loop_queue *queue = hctx->driver_data;
 	struct request *req = bd->rq;
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
-	int ret;
+	blk_status_t ret;
 
 	ret = nvme_setup_cmd(ns, req, &iod->cmd);
-	if (ret != BLK_MQ_RQ_QUEUE_OK)
+	if (ret)
 		return ret;
 
 	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
@@ -179,16 +175,15 @@ static int nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		nvme_cleanup_cmd(req);
 		blk_mq_start_request(req);
 		nvme_loop_queue_response(&iod->req);
-		return BLK_MQ_RQ_QUEUE_OK;
+		return BLK_STS_OK;
 	}
 
 	if (blk_rq_bytes(req)) {
 		iod->sg_table.sgl = iod->first_sgl;
-		ret = sg_alloc_table_chained(&iod->sg_table,
+		if (sg_alloc_table_chained(&iod->sg_table,
 				blk_rq_nr_phys_segments(req),
-				iod->sg_table.sgl);
-		if (ret)
-			return BLK_MQ_RQ_QUEUE_BUSY;
+				iod->sg_table.sgl))
+			return BLK_STS_RESOURCE;
 
 		iod->req.sg = iod->sg_table.sgl;
 		iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl);
@@ -197,7 +192,7 @@ static int nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_mq_start_request(req);
 
 	schedule_work(&iod->work);
-	return BLK_MQ_RQ_QUEUE_OK;
+	return BLK_STS_OK;
 }
 
 static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
@@ -234,15 +229,10 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set,
 		struct request *req, unsigned int hctx_idx,
 		unsigned int numa_node)
 {
-	return nvme_loop_init_iod(set->driver_data, blk_mq_rq_to_pdu(req),
-			hctx_idx + 1);
-}
+	struct nvme_loop_ctrl *ctrl = set->driver_data;
 
-static int nvme_loop_init_admin_request(struct blk_mq_tag_set *set,
-		struct request *req, unsigned int hctx_idx,
-		unsigned int numa_node)
-{
-	return nvme_loop_init_iod(set->driver_data, blk_mq_rq_to_pdu(req), 0);
+	return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req),
+			(set == &ctrl->tag_set) ? hctx_idx + 1 : 0);
 }
 
 static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
@@ -280,7 +270,7 @@ static const struct blk_mq_ops nvme_loop_mq_ops = {
 static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
 	.queue_rq	= nvme_loop_queue_rq,
 	.complete	= nvme_loop_complete_rq,
-	.init_request	= nvme_loop_init_admin_request,
+	.init_request	= nvme_loop_init_request,
 	.init_hctx	= nvme_loop_init_admin_hctx,
 	.timeout	= nvme_loop_timeout,
 };
@@ -467,7 +457,7 @@ static int __nvme_loop_del_ctrl(struct nvme_loop_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
 		return -EBUSY;
 
-	if (!schedule_work(&ctrl->delete_work))
+	if (!queue_work(nvme_wq, &ctrl->delete_work))
 		return -EBUSY;
 
 	return 0;
@@ -501,8 +491,8 @@ static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl)
 
 static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 {
-	struct nvme_loop_ctrl *ctrl = container_of(work,
-					struct nvme_loop_ctrl, reset_work);
+	struct nvme_loop_ctrl *ctrl =
+		container_of(work, struct nvme_loop_ctrl, ctrl.reset_work);
 	bool changed;
 	int ret;
 
@@ -540,21 +530,6 @@ out_disable:
 	nvme_put_ctrl(&ctrl->ctrl);
 }
 
-static int nvme_loop_reset_ctrl(struct nvme_ctrl *nctrl)
-{
-	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl);
-
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
-		return -EBUSY;
-
-	if (!schedule_work(&ctrl->reset_work))
-		return -EBUSY;
-
-	flush_work(&ctrl->reset_work);
-
-	return 0;
-}
-
 static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 	.name			= "loop",
 	.module			= THIS_MODULE,
@@ -562,11 +537,9 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
-	.reset_ctrl		= nvme_loop_reset_ctrl,
 	.free_ctrl		= nvme_loop_free_ctrl,
 	.submit_async_event	= nvme_loop_submit_async_event,
 	.delete_ctrl		= nvme_loop_del_ctrl,
-	.get_subsysnqn		= nvmf_get_subsysnqn,
 };
 
 static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -629,15 +602,13 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	INIT_LIST_HEAD(&ctrl->list);
 
 	INIT_WORK(&ctrl->delete_work, nvme_loop_del_ctrl_work);
-	INIT_WORK(&ctrl->reset_work, nvme_loop_reset_ctrl_work);
+	INIT_WORK(&ctrl->ctrl.reset_work, nvme_loop_reset_ctrl_work);
 
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops,
 				0 /* no quirks, we're perfect! */);
 	if (ret)
 		goto out_put_ctrl;
 
-	spin_lock_init(&ctrl->lock);
-
 	ret = -ENOMEM;
 
 	ctrl->ctrl.sqsize = opts->queue_size - 1;
@@ -766,7 +737,7 @@ static void __exit nvme_loop_cleanup_module(void)
 		__nvme_loop_del_ctrl(ctrl);
 	mutex_unlock(&nvme_loop_ctrl_mutex);
 
-	flush_scheduled_work();
+	flush_workqueue(nvme_wq);
 }
 
 module_init(nvme_loop_init_module);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 8ff6e430b30a..747bbdb4f9c6 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -47,6 +47,7 @@ struct nvmet_ns {
 	u32			blksize_shift;
 	loff_t			size;
 	u8			nguid[16];
+	uuid_t			uuid;
 
 	bool			enabled;
 	struct nvmet_subsys	*subsys;
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 9e45cde63376..56a4cba690b5 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1027,7 +1027,7 @@ nvmet_rdma_parse_cm_connect_req(struct rdma_conn_param *conn,
 	queue->recv_queue_size = le16_to_cpu(req->hsqsize) + 1;
 	queue->send_queue_size = le16_to_cpu(req->hrqsize);
 
-	if (!queue->host_qid && queue->recv_queue_size > NVMF_AQ_DEPTH)
+	if (!queue->host_qid && queue->recv_queue_size > NVME_AQ_DEPTH)
 		return NVME_RDMA_CM_INVALID_HSQSIZE;
 
 	/* XXX: Should we enforce some kind of max for IO queues? */
@@ -1307,53 +1307,44 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id,
 
 /**
  * nvme_rdma_device_removal() - Handle RDMA device removal
+ * @cm_id:	rdma_cm id, used for nvmet port
  * @queue:      nvmet rdma queue (cm id qp_context)
- * @addr:	nvmet address (cm_id context)
  *
  * DEVICE_REMOVAL event notifies us that the RDMA device is about
- * to unplug so we should take care of destroying our RDMA resources.
- * This event will be generated for each allocated cm_id.
+ * to unplug. Note that this event can be generated on a normal
+ * queue cm_id and/or a device bound listener cm_id (where in this
+ * case queue will be null).
  *
- * Note that this event can be generated on a normal queue cm_id
- * and/or a device bound listener cm_id (where in this case
- * queue will be null).
- *
- * we claim ownership on destroying the cm_id. For queues we move
- * the queue state to NVMET_RDMA_IN_DEVICE_REMOVAL and for port
+ * We registered an ib_client to handle device removal for queues,
+ * so we only need to handle the listening port cm_ids. In this case
  * we nullify the priv to prevent double cm_id destruction and destroying
  * the cm_id implicitely by returning a non-zero rc to the callout.
  */
 static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id,
 		struct nvmet_rdma_queue *queue)
 {
-	unsigned long flags;
-
-	if (!queue) {
-		struct nvmet_port *port = cm_id->context;
+	struct nvmet_port *port;
 
+	if (queue) {
 		/*
-		 * This is a listener cm_id. Make sure that
-		 * future remove_port won't invoke a double
-		 * cm_id destroy. use atomic xchg to make sure
-		 * we don't compete with remove_port.
-		 */
-		if (xchg(&port->priv, NULL) != cm_id)
-			return 0;
-	} else {
-		/*
-		 * This is a queue cm_id. Make sure that
-		 * release queue will not destroy the cm_id
-		 * and schedule all ctrl queues removal (only
-		 * if the queue is not disconnecting already).
+		 * This is a queue cm_id. we have registered
+		 * an ib_client to handle queues removal
+		 * so don't interfear and just return.
 		 */
-		spin_lock_irqsave(&queue->state_lock, flags);
-		if (queue->state != NVMET_RDMA_Q_DISCONNECTING)
-			queue->state = NVMET_RDMA_IN_DEVICE_REMOVAL;
-		spin_unlock_irqrestore(&queue->state_lock, flags);
-		nvmet_rdma_queue_disconnect(queue);
-		flush_scheduled_work();
+		return 0;
 	}
 
+	port = cm_id->context;
+
+	/*
+	 * This is a listener cm_id. Make sure that
+	 * future remove_port won't invoke a double
+	 * cm_id destroy. use atomic xchg to make sure
+	 * we don't compete with remove_port.
+	 */
+	if (xchg(&port->priv, NULL) != cm_id)
+		return 0;
+
 	/*
 	 * We need to return 1 so that the core will destroy
 	 * it's own ID.  What a great API design..
@@ -1519,9 +1510,51 @@ static struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.delete_ctrl		= nvmet_rdma_delete_ctrl,
 };
 
+static void nvmet_rdma_add_one(struct ib_device *ib_device)
+{
+}
+
+static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
+{
+	struct nvmet_rdma_queue *queue;
+
+	/* Device is being removed, delete all queues using this device */
+	mutex_lock(&nvmet_rdma_queue_mutex);
+	list_for_each_entry(queue, &nvmet_rdma_queue_list, queue_list) {
+		if (queue->dev->device != ib_device)
+			continue;
+
+		pr_info("Removing queue %d\n", queue->idx);
+		__nvmet_rdma_queue_disconnect(queue);
+	}
+	mutex_unlock(&nvmet_rdma_queue_mutex);
+
+	flush_scheduled_work();
+}
+
+static struct ib_client nvmet_rdma_ib_client = {
+	.name   = "nvmet_rdma",
+	.add = nvmet_rdma_add_one,
+	.remove = nvmet_rdma_remove_one
+};
+
 static int __init nvmet_rdma_init(void)
 {
-	return nvmet_register_transport(&nvmet_rdma_ops);
+	int ret;
+
+	ret = ib_register_client(&nvmet_rdma_ib_client);
+	if (ret)
+		return ret;
+
+	ret = nvmet_register_transport(&nvmet_rdma_ops);
+	if (ret)
+		goto err_ib_client;
+
+	return 0;
+
+err_ib_client:
+	ib_unregister_client(&nvmet_rdma_ib_client);
+	return ret;
 }
 
 static void __exit nvmet_rdma_exit(void)
@@ -1544,6 +1577,7 @@ static void __exit nvmet_rdma_exit(void)
 	mutex_unlock(&nvmet_rdma_queue_mutex);
 
 	flush_scheduled_work();
+	ib_unregister_client(&nvmet_rdma_ib_client);
 	ida_destroy(&nvmet_rdma_queue_ida);
 }